Alexandra Pomares Quimbaya

• Pontifical Xavierian University

The growing popularity of social networking platforms worldwide has substantially increased the presence of offensive language on these platforms. To date, most of the systems developed to mitigate this challenge focus primarily on English content. However, this issue is a global concern, and therefore, other languages, such as Spanish, are involve...

Several studies reported in the literature have analyzed the usefulness of various sources of information to predict the price of stock markets. Some of them have focused attention on the predictive power of information from social networks, which by their nature is unstructured and present a large volume of data. However, capturing and processing...

The banking sector has been one of the first to identify the importance of social media analysis to understand customers' needs to offer new services, segment the market, build customer loyalty, or understand their requests. Users of Social Networking Sites (SNS) have interactions that can be analyzed to understand the relationships between people...

This research aims to analyze the Digital Social Networks (DSN) behavior, constructed from the network’s relationships, interactions, and expressions of users’ private states through collective subjectivity. For this purpose, an onion-ring system called COSSOL has been built in a case study for Twitter, following a hybrid approach to integrate Mach...

Uno de los fenómenos de estudio que ha motivado a sociólogos, antropólogos, psicólogos y, en general, a investigadores interesados en las interacciones humanas y los alcances de la comunicación lo constituye el Análisis de Subjetividad Colectiva. Las redes sociales son actualmente la principal plataforma para “escuchar” modos de pensar, actuar y se...

Digital social networks have become an essential source of information because celebrities use them to share their opinions, ideas, thoughts, and feelings. This makes digital social networks one of the preferred means for celebrities to promote themselves and attract new followers. This paper proposes a model of feature selection for the classifica...

Transfer learning has demonstrated its potential in natural language processing tasks, where models have been pre-trained on large corpora and then tuned to specific tasks. We applied pre-trained transfer models to a Spanish biomedical document classification task. The main goal is to analyze the performance of text classification by clinical speci...

Background Controlled vocabularies are fundamental resources for information extraction from clinical texts using natural language processing (NLP). Standard language resources available in the healthcare domain such as the UMLS metathesaurus or SNOMED CT are widely used for this purpose, but with limitations such as lexical ambiguity of clinical t...

The emergence of digital social networks has transformed society, social groups, and institutions in terms of the communication and expression of their opinions. Determining how language variations allow the detection of communities, together with the relevance of specific vocabulary (proposed by the National Council of Accreditation of Colombia (C...

The explosive growth of fake news on social networks has aroused great interest from researchers in different disciplines. To achieve efficient and effective detection of fake news requires scientific contributions from various disciplines , such as computational linguistics, artificial intelligence, and sociology. Here we illustrate how polarity,...

Acronyms frequently occur in clinical text, which makes their identification, disambiguation and resolution an important task in clinical natural language processing. This paper contributes to acronym resolution in Spanish through the creation of a set of sense inventories organized by clinical specialty containing acronyms, their expansions, and c...

Achieving accurate stock market models can provide investors with tools for making better data-based decisions. These models can help traders to reduce investment risk and select the most profitable stocks. Furthermore, creating advanced models enable the usage of non-traditional data like historical stock prices and news. There are several review...

Extracting valuable knowledge from Electronic Health Records (EHR) represents a challenging task due to the presence of both structured and unstructured data, including codified fields, images and test results. Narrative text in particular contains a variety of notes which are diverse in language and detail, as well as being full of ad hoc terminol...

Introducción: La literatura pedagógica propone los juegos serios (serious games) como herramientas efectivas para el aprendizaje; sin embargo, los estudia como si fueran productos homogéneos que se diferencian solo por la temática. Así, sus diseños no se discuten y se dejan a la discreción de cada profesor-creador. Objetivo: Establecer la relación...

Unfortunately, in social networks, software bots or just bots are becoming more and more common because malicious people have seen their usefulness to spread false messages, spread rumors and even manipulate public opinion. Even though the text generated by users in social networks is a rich source of information that can be used to identify differ...

Social networks have been a revolutionary scenario for celebrities because they allow them to reach a wider audience with much higher frequency than using traditional means. These platforms enable them to improve or sometimes deteriorate, their careers through the construction of closer relationships with their fans and the acquisition of new ones....

Social networks have been a revolutionary scenario for celebrities because they allow them to reach a wider audience with much higher frequency than using traditional means. These platforms enable them to improve or sometimes deteriorate, their careers through the construction of closer relationships with their fans and the acquisition of new ones....

Unfortunately, in social networks, software bots or just bots are becoming more and more common because malicious people have seen their usefulness to spread false messages, spread rumors and even manipulate public opinion. Even though the text generated by users in social networks is a rich source of information that can be used to identify differ...

Background: The identification of sections in narrative content of Electronic Health Records (EHR) has demonstrated to improve the performance of clinical extraction tasks; however, there is not yet a shared understanding of the concept and its existing methods. The objective is to report the results of a systematic review concerning approaches ai...

Objective: Assessment of the pedagogical effect and technological acceptance of the serious game, CODIFICO, which has been designed to train medical students in ICD-10 diagnosis coding. Materials and Methods: We designed the serious game, CODIFICO, as an alternative way to teach ICD-10 diagnosis coding to undergraduate medical students. To assess...

When a company requires analytical capabilities using data that might include sensitive information, it is important to use a solution that protects those sensitive portions, while maintaining its usefulness. An analysis of existing anonymization approaches found out that some of them only permit to disclose aggregated information about large group...

Food related consumer behavior is a topic of major interest to areas such as health and marketing. Social media offers a scenario in which people share information about preferences, interests and motivations about eating habits and food products that have not been exploded as appropriate. In this work we present an algorithm to exploit the potenti...

Objetivo: La implementación de las guías de práctica clínica está limitada por la falta de herramientas que faciliten los procesos de auditoría y retroalimentación a los profesionales de salud. Este estudio evalúa la herramienta automatizada (EXEMED), diseñada para valorar la adherencia a las guías de práctica clínica a partir de la información con...

Text classification or text categorization in social networks such as Twitter has taken great importance with the growth of applications of this process in diverse domains of society. Literature about text classifiers is significantly wide especially in languages such as English; however, this is not the case for age classification whose studies ha...

Introduction: The literature shows an optimistic landscape for the effectiveness of games in medical education. Nevertheless, games are not considered mainstream material in medical teaching. Two research questions that arise are the following: What pedagogical strategies do developers use when creating games for medical education? And what is the...

Extracting valuable knowledge from Electronic Health Records (EHR) represents a challenging task due to the presence of both structured and unstructured data, including codified fields, images and test results. Narrative text in particular contains a variety of notes which are diverse in language and detail, as well as being full of ad hoc terminol...

A corpus is an indispensable linguistic resource for any application of natural language processing. Some corpora have been created manually or semi-automatically for a specific domain. In this paper, we present an automatic approach to generate corpus from digital information sources such as Wikipedia and web pages. The information extracted by Wi...

p> Objective : Electronic medical records (EMR) typically contain both structured attributes as well as narrative text. The usefulness of EMR for research and administration is hampered by the difficulty in automatically analyzing their narrative portions. Accordingly, this paper proposes SPIRE, a strategy for prioritizing EMR, using natural langua...

Medical practice, monitoring and control guidelines enable standardization, assessment and quality improvementin healthcare. This often implies collecting and analyzing electronic medical records (EMRs)in order to calculate compliance metrics and support evidence-based decision-making. However, forthese benefits to materialize a set of challenges m...

Speech is the natural communication means, however, it is not the typical input means afforded by computers. The interaction between humans and machines would have become easier, if speech were an alternative effective input means to the keyboard and mouse. With advancement in techniques for signal processing and model building and the empowerment...

Improving information systems and guaranteeing the quality of health services are current challenges for global governments. Financing problems and congestion in health care centers, increased demand for services due to aging population, mobility issues and insecurity, risks of accidents and contagion of diseases in care centers are some of the pro...

En este proyecto se presenta un constructor automático de modelos de dominios de conocimientos de forma automática sin corpus preexistente para describir semánticamente un contexto. El constructor está basado en técnicas y métodos para la construcción de corpus a partir de fuentes digitales, mediante el desarrollo de librerías de software que autom...

In health care information systems, electronic health records are an important part of the knowledge concerning individual health histories. Extracting valuable knowledge from these records represents a challenging task because they are composed of data of different kind: images, test results, narrative texts that include both highly codified and a...

Las historias clinicas electronicas contienen informacion importante de un paciente, que puede servir de insumo para realizar analisis retrospectivo en el diagnostico, seguimiento y tratamiento de una enfermedad. Esta informacion es registrada de forma narrativa con lo que surge la limitacion para identificar eventos medicos (tales como citas medic...

The obstacles for using the extensive narrative data found within EMR in research projects, mainly due to their lack of structure and standardization, have motivated different types of works. This chapter presents projects that have demonstrated successful use of Natural Language Processing (NLP) and/or data mining techniques for the exploitation o...

This paper presents EXEMED v2, a system that allows the evaluation of clinical practice guideline indicators. EXEMED v2 includes a knowledge base that supports the definition of executable rules applied over Electronic Health Records (EHR) in order to measure its compliance with a specific clinical guideline. Taking into account that an EHR may inc...

Purpose – This paper aims to present a detailed description of Agents for Enriching Services (AES), an agent-oriented framework that allows adapting a service in an information system. AES provides an adaptation logic that can be instantiated and extended to be useful in different domains. In previous works, we presented the adaptation mechanism o...

Dynamic Adaptive Activity Planning is a technique to create plans in which activities are the best suited for particular users and their context. This paper presents an architecture, called ASHYI, for dynamic adaptive activity planning, and ASHYI-EDU, an application of ASHYI for the educational domain. ASHYI-EDU can automatically create a learning...

This paper presents EXEMED v2, a system that allows the evaluation of clinical practice guideline indicators. EXEMED v2 includes a knowledge base that supports the definition of executable rules applied over Electronic Health Records (EHR) in order to measure its compliance with a specific clinical guideline. Taking into account that an EHR may inc...

In the healthcare domain the analysis of Electronic Medical Records (EMR) may be classified as a Big Data problem since it has the three fundamental characteristics: Volume, Variety and Speed. A major drawback is that most of the information contained in medical records is narrative text, where natural language processing and text mining are key te...

Development of IT-based services to support decision-making in healthcare should be guided by the following considerations: rigor, relevance, user-centered participation and inclusion of the best practices for IT-based service systems. In this paper, the balance between rigor and relevance is achieved by following the design science research method...

This paper presents EXEMED v2, a system that allows the evaluation of clinical practice guideline indicators. EXEMED v2 includes a knowledge base that supports the definition of executable rules applied over Electronic Health Records (EHR) in order to measure its compliance with a specific clinical guideline. Taking into account that an EHR may inc...

This paper presents EXEMED, a knowledge base created for the definition of executable rules that can be applied over Electronic Health Records (EHR) in order to measure the EHR compliance with respect to a specific clinical guideline. EXEMED is based on description logic and provides the concepts and roles necessary to express the sets of patients...

This chapter presents a health decision-support system called DISEArch that allows the identification and analysis of relevant EHR for decision-making. It uses structured and non-structured data, and provides analytical as well as visualization facilities over individual or sets of EHR. DISEArch proves to be useful to empower researchers during ana...

The correct construction of E-Health applications in order to support medical work is vital, because these systems are the basis for making decisions that impact patients' lives. In order to construct quality software it’s necessary from the requirements phase to clarify the use to be given to these systems and how to properly manage them. In this...

Development of IT-based services to support decision-making in healthcare should be guided by the following considerations: rigor, relevance, user-centered participation and inclusion of the best practices for IT-based service systems. In this paper, the balance between rigor and relevance is achieved by following the design science research method...

licenses/by-nc-nd/3.0/). Peer-review under responsibility of the Organizing Committee of CENTERIS 2014. Abstract This paper presents EXEMED, a knowledge base created for the definition of executable rules that can be applied over Electronic Health Records (EHR) in order to measure the EHR compliance with respect to a specific clinical guideline. EX...

The extraction of metadata used during the planning phase in mediation systems assumes the existence of a metadata repository that in most cases must be created with high human involvement. This dependency rises complexity of maintenance of the system and therefore the reliability of the metadata itself. This article presents MetaExtractor, a syste...

One of the most important inputs for medical research is the information registered in electronic medical records. This information typically contains sensitive data that must be preserved in order to be used for research or educational purposes, and protected depending on the regulations of each country and institution. In order to assure confiden...

Although ontologies have been used in a considerable number of knowledge management projects, in most of them their application has been limited to the definition of a common organizational language. This chapter offers an alternative view on the use of ontologies, supporting all of the knowledge management processes, including generation, acquisit...

One of the most important inputs for medical research is the information registered in electronic medical records. This information typically contains sensitive data that must be preserved in order to be used for research or educational purposes, depending on the regulations of each country and institution. In order to assure confidentiality of dat...

This paper presents ADDOCO: an adapted data distribution model for collaborative mobile applications. The object of ADDOCO is to provide a dynamic data distribution in collaborative environments, based on mobile technologies. In order to support effective distributed collaboration, ADDOCO is based on a data-centric model that allows change dynamica...

The processes developed in collaborative environments involve numerous resources that must be shared according to the confidentiality, distribution and replication requirements of each process. Current proposals to manage resources in collaborative environments have limitations handling these requirements. In most cases, there are general policies...

This paper presents a strategy for the analysis of landmine events, combining spatial data mining (SDM) and Geographic Information Systems (GIS) in an enriched data environment. This strategy allows to acquire useful information to improve the prevention, detection and response to the problems of planning humanitarian demining operations in Colombi...

The AYLLU collaboration model aims people that behave as cooperative rational agents supported by software agents working as mediators. The interaction protocols used for collaboration purposes are semantic and well-structured. However, for real world situations, these features are not enough to support the requirements of group work. The general A...

This paper proposes DISEArch, a novel strategy for searching electronic health records (EHR) of patients that have a specific disease. The objective of DISEArch is to enhance research activities on disease analysis allowing researchers to describe the disease they are interested on, and providing them the EHRs that best match their description. Its...

Nowadays users receive a huge amount of data from different information systems that do not consider characteristics of the user such as location or device. This overwhelming amount of data difficult users to obtain relevant information fitting their needs and own characteristics and, in some cases, the information cannot be displayed because it do...

Ontology-Based Applications for Enterprise Systems and Knowledge Management provides an opportunity for readers to clearly understand the notion of ontology engineering and the practical aspects of this approach in the domains of two interest areas: Knowledge Management Systems and Enterprise Systems. A perfect reference for researchers, scholars,...

One of the current challenges in information technology is to provide instant access to relevant information, without being limited by the location of the user or the device used to retrieve it. Current technologies allow users to access an overwhelming amount of data. This is an undesirable situation, since it is very difficult for users to obtain...

This paper presents a strategy for adapting the ex- ecution coordination process in mediation systems. This strategy was designed for distributed data environments, typical of virtual organizations, where the vertical and horizontal fragmentation is not disjoint. The principle of the adaptation strategy is to dynamically choose the sources particip...

This paper concerns querying in large scale virtual organizations. Such organizations are characterized by a challenging data context involving a large number of distributed data sources with strong heterogeneity and uncontrolled data overlapping. In that context, data source selection during query evaluation is particularly important and complex....

This paper presents OptiSource, a novel approach of source selection that reduces the number of data sources accessed during query evaluation in complex large scale distributed data contexts in virtual organizations (VO). In these contexts autonomous organizations share data about a group of domain concepts (e.g. patient, client, gene). The instanc...

This paper presents OptiSource, a novel approach of source selection that reduces the number of data sources accessed during query evaluation in large scale distributed data contexts. These contexts are typical of large scale Virtual Organizations (VO) where autonomous organizations share data about a group of domain concepts (e.g. patient, gene)....

Data source selection is one of the most critical processes in mediation systems for large-scale contexts, as those found in large virtual organizations. In such contexts, the high volume of structured data sources, distribution, heterogeneity, fragmentation and replication of data hinder the identification of the relevant data sources that should...

This work concerns query processing to support data sharing in large scale Virtual Organizations(VO). Characterization of VO’s data sharing contexts reflects the coexistence of factors like sources overlapping, uncertain data location, and fuzzy copies in dynamic large scale environments that hinder query processing. Existing results on distributed...

This paper proposes ORS, an original strategy to reduce the number of data sources to access during query evaluation in large scale mediation systems. ORS proceeds first selecting sources using extensional (data) information to discard useless sources and then validates the intentional (schema) information that each one is able to provide. The firs...

This paper presents an approach of data integration in Health Virtual Organization (HVO). It targets large scale contexts where high distribution and autonomy of sources produce complex integration scenarios. The principle is to provide a high conceptual level composed of Virtual Data Objects (VDO) that can be queried independently of the data sour...

This article presents PASTEUR, a system of indexing and localization of software components on large scale that promotes the commerce of components, in open, dynamic and heterogeneous environment. Its design and implementation are supported in the technology of systems P2P DHT from which it takes the distributed lookup and distributed storage servi...